Text to Audio Converter for Modern Healthcare Teams

By Clinical Audio editorial team · Updated 2026-11-18

Clinical Audio delivers a reliable text-to-speech API designed for healthcare teams creating large-scale audio patient guides and internal training materials. We handle the volume and language diversity required for global medical communication without compromising on clarity or data privacy. Our solution ensures consistent voice quality across diverse document sets, making complex medical information accessible to patients and staff alike.

On this page, you will find the technical specifications, pricing details, and integration workflows necessary to deploy our API into your existing systems. Whether you are generating consent forms, multilingual discharge instructions, or training modules, Clinical Audio provides the infrastructure to scale your audio content production efficiently. Explore our documentation to begin integrating today.

Text to Audio Converter for Modern Healthcare Teams

Frequently asked questions

Is Clinical Audio a text to audio converter?

Clinical Audio is a cloud text-to-speech API. You send text via a POST request and receive an audio file. The endpoint matches the OpenAI speech endpoint shape, allowing you to use official OpenAI SDKs by adjusting the base URL to https://api.play79z.com/v1. It is designed for generating audio files from text inputs efficiently.

How many languages does the API support?

The API supports 23 languages, including English, Spanish, French, German, Chinese, Japanese, Arabic, Hindi, and Portuguese. Any voice can speak any of these languages. If the language parameter is omitted, the system guesses from the script, defaulting to English for Latin text. Languages like Vietnamese and Ukrainian are not supported.

Can I use the API for patient-facing content?

Yes, the API is suitable for patient-facing content like medical guides. Generated files carry an inaudible watermark marking them as synthetic speech. Input text is used only for synthesis and not for training. The clear, neutral voices like Atlas or Sage are ideal for instructional patient materials requiring high clarity.

What is the character limit per request?

Each request accepts up to 4096 characters of input text. For longer texts, you must split them into parts of this size and join the resulting audio files. Spaces and punctuation count toward the character limit. This ensures consistent processing performance for each individual synthesis request.

Does the API support medical terminology?

The API uses eight preset voices based on licensed recordings from LibriVox. It does not offer custom pronunciation lexicons or SSML to manually adjust specific medical term pronunciations. However, the clear narration styles of voices like Aria or Sage generally handle standard medical terminology well through natural speech patterns.

How is data used during synthesis?

Input text is used solely to produce the audio file and is not used for training models. The generated audio is returned in the response and not stored on our servers. We retain request metadata, such as time, character count, and status, strictly for billing purposes.

Can I generate audio in bulk?

Yes, you can generate audio in bulk by splitting longer texts into 4096-character segments. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time, generating about 25 characters of text per second of audio for long texts.

What audio formats are available?

You can request audio in five formats: mp3, wav, opus, flac, and pcm. These formats are specified in the response_format field of your API request. This allows you to choose the optimal format for your specific healthcare platform or internal training infrastructure requirements.

Is there a free trial available?

Signing in with Google provides a $0.50 free trial credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without this trial credit. The trial allows you to test the API’s quality and integration before committing to paid usage.

How do I pay for the API?

Payment is processed via USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and funds are credited automatically within minutes. We do not accept credit cards, PayPal, or subscriptions. There are no invoices with VAT, and your balance does not expire.

Are there any monthly fees?

There are no monthly fees, no seats, and no minimum spend. You pay $0.01 per 1,000 characters, with failed requests being free. You can top up as needed, and the balance remains available until used. This pay-as-you-go model suits variable usage patterns in healthcare teams.

Can I adjust the speech speed?

Yes, you can adjust the speech speed using the speed parameter, which accepts values between 0.25 and 4.0. This allows you to slow down complex medical instructions for better patient comprehension or speed up internal training materials. The default speed is 1.0.

What happens if a request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry the request or adjust parameters like input text or voice as needed.

Does the API support SSML?

No, the API does not support SSML. It also lacks phoneme dictionaries or custom pronunciation lexicons. You control speech characteristics primarily through voice selection and speed adjustment. For precise control over pauses or emphasis, you may need to split text into separate requests.

First request

curl

curl https://api.play79z.com/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Why healthcare teams choose API-driven audio

Sound wave illustration for: Why healthcare teams choose API-driven audio

Healthcare teams rely on Clinical Audio to maintain a consistent voice across thousands of patient guides. By centralizing audio generation through a single API, medical communicators ensure tone and quality remain uniform across all materials, from discharge instructions to chronic care management videos.

Consistent voice across patient guides

A unified voice profile eliminates the jarring experience of switching between different narrator styles within a single patient journey. Whether using the calm, instructional tone of Sage or the warm clarity of Aria, teams can standardize how medical information sounds across all departments and facilities.

Bulk generation for large document sets

The API accepts text up to 4096 characters per request, allowing teams to process entire sections of medical manuals or consent forms efficiently. Requests are processed sequentially, ensuring reliable delivery even under load, while the ability to split and join audio files handles documents of any length.

  • Handle large document sets by splitting text into 4096-character chunks.
  • Sequential processing ensures reliable audio delivery without data loss.
  • Join generated audio files seamlessly for complete narrative flow.

Multi-language support for diverse populations

Supporting 23 languages, the API serves diverse patient populations without requiring separate voice hiring. From English and Spanish to Arabic and Japanese, the system handles language detection or allows explicit setting, ensuring medical terminology is articulated correctly across major global markets and niche linguistic groups.

  • Generate audio in 23 languages, including major markets and niche dialects.
  • Automatic language detection or explicit ISO code setting for accuracy.
  • Supports diverse populations with native-sounding synthesis for key regions.

Clinical-grade voices for clear communication

Sound wave illustration for: Clinical-grade voices for clear communication

Clinical Audio offers eight voice presets designed for clarity and comprehension in medical contexts. Each voice is based on licensed recordings from LibriVox public-domain audiobook readings, ensuring a consistent and professional auditory experience for patient guides and internal training materials.

The system does not use phoneme dictionaries or custom lexicons, relying instead on the inherent clarity of the voice models to handle medical terminology effectively. This approach eliminates the need for complex pronunciation tuning while maintaining high intelligibility for complex terms.

Neutral and calming voice presets

We provide eight distinct voices, including neutral options like Atlas for news-style delivery and calm voices like Sage for instructional content. Female presets such as Luna offer a soft, storytelling tone suitable for sensitive patient guides, while Felix provides an energetic option for promotional health content.

These voices are based on licensed recordings, ensuring authenticity without the need for custom cloning or emotion tags. Users can select the tone that matches their specific communication needs, from formal medical updates to conversational instructions.

  • Atlas: Neutral, news-style delivery
  • Sage: Calm, instructional tone
  • Luna: Soft, storytelling voice
  • Aria: Warm, clear narrator

High clarity for medical terminology

The TTS engine processes text up to 4096 characters per request, ensuring that complex medical terms are rendered clearly without requiring additional configuration. The voices are based on licensed recordings, providing a natural flow that aids in understanding dense information.

No phoneme dictionaries or custom lexicons are needed, simplifying the integration process. The system handles language detection automatically, though users can explicitly set the language code for non-English Latin-script text to ensure accuracy.

Adjustable speed for different patient needs

Users can adjust the playback speed between 0.25 and 4.0 times normal speed. This flexibility allows healthcare teams to tailor audio content for diverse patient populations, from slower-paced instructions for elderly patients to faster summaries for staff training.

The API returns audio files in formats like MP3, WAV, or FLAC, ensuring compatibility with various digital health platforms. Failed requests are free, ensuring no cost is incurred for errors during the generation process.

Clinical-grade voices for clear communication

Supported languages for global reach

Sound wave illustration for: Supported languages for global reach

Clinical Audio supports 23 languages, enabling healthcare teams to deliver patient guides and training materials to diverse populations without compromising clarity. Whether targeting major markets or niche regions, the API ensures consistent voice quality across all supported dialects.

The system handles language diversity efficiently, allowing medical teams to scale communication globally. With native-sounding synthesis for key regions, clinical instructions remain precise and understandable, reducing miscommunication risks in multilingual hospital environments.

English, Spanish, and French for major markets

Our API natively supports English, Spanish, and French, covering the majority of global healthcare interactions. These languages are optimized for clear articulation of medical terminology, ensuring that critical patient instructions are understood accurately.

Teams can generate large batches of patient guides in these languages simultaneously, maintaining consistent voice characteristics across all documents. This consistency helps patients recognize familiar audio cues, improving compliance with treatment plans.

  • Optimized for medical terminology clarity
  • Consistent voice across all documents
  • Ideal for high-volume patient guides

23 languages including German, Japanese, and Arabic

Beyond major markets, Clinical Audio supports 21 additional languages, including German, Japanese, and Arabic. This extensive list includes Arabic, Chinese, Danish, Dutch, Finnish, Greek, Hebrew, Hindi, Italian, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Swahili, Swedish, and Turkish.

Each voice preset is trained to handle the phonetic nuances of these languages, ensuring natural-sounding speech. Healthcare teams can create localized training modules and patient education materials for diverse patient demographics without hiring multiple voice actors.

  • 23 total languages supported
  • Includes Arabic, Chinese, Japanese, and more
  • Natural phonetic handling for each language

Automatic language detection or explicit setting

The API automatically detects the language from the input text script, defaulting to English for Latin-script text if not specified. For non-English Latin-script text, such as German or French, you should explicitly set the language code to ensure accurate pronunciation.

This flexibility allows developers to streamline integration. For example, a system generating discharge instructions for a multilingual hospital can dynamically set the language parameter based on patient preference, ensuring the audio matches the patient's primary language.

  • Automatic detection for Latin scripts
  • Explicit language setting for accuracy
  • Supports ISO language codes

How the API integrates with your workflow

Sound wave illustration for: How the API integrates with your workflow

To integrate Clinical Audio into your medical workflows, you can leverage the familiar OpenAI SDK by simply updating the base_url to https://api.play79z.com/v1. This allows existing engineering teams to adopt the API with minimal code changes, ensuring consistent voice across patient guides and internal training materials without learning a new library.

Requests are structured as standard JSON bodies, making it easy to automate bulk generation for large document sets. You can pass text directly from your electronic health record systems or content management tools, receiving audio files in formats like MP3 or WAV that are ready for immediate distribution to patients or staff.

OpenAI SDK compatibility for easy setup

By changing the base_url in the official OpenAI SDK to https://api.play79z.com/v1, your team can use familiar methods to send text and receive audio. This compatibility means you do not need to rewrite existing integrations or train developers on a proprietary client, accelerating deployment for healthcare IT teams managing multiple audio projects.

JSON-based requests for automation

Every request uses a standard JSON structure with fields for model, input, voice, and response_format. This predictable shape allows seamless automation scripts to loop through hundreds of patient discharge instructions or consent forms, processing them in batches while handling rate limits of 60 requests per minute per key.

Generation speed for dynamic content

Text synthesis typically runs at roughly real-time speed, generating about 25 characters of text per second of audio. For dynamic content like appointment reminders or quick updates, this speed ensures that audio files are produced quickly enough to be used in real-time patient communication flows without significant user delay.

Pricing built for high-volume usage

Sound wave illustration for: Pricing built for high-volume usage

Healthcare teams need predictable costs without paying for idle capacity. Clinical Audio charges $0.01 per 1,000 characters, ensuring you only pay for what you generate. With no monthly minimums or subscription fees, this model scales efficiently whether you are producing a few patient leaflets or thousands of training modules.

Pay per character with no monthly minimums

Your billing is directly tied to usage. Failed requests are free, so you never pay for errors. This transparent structure eliminates the risk of overpaying for unused credits, making it ideal for teams with fluctuating audio production needs.

Free trial credit for initial testing

New accounts created via Google sign-in receive $0.50 in trial credit, valid for 7 days. This provides approximately 50,000 characters to test voice quality and integration speed before committing to larger volumes.

Transparent billing with USDT top-up

Top-ups are processed via USDT on the TRON network (TRC-20) with a minimum deposit of $5. Funds are credited automatically within minutes. There are no invoices, VAT complexities, or hidden transaction fees, keeping your accounting straightforward.

Pricing built for high-volume usage

Data privacy and security for medical data

Sound wave illustration for: Data privacy and security for medical data

Clinical Audio processes input text exclusively to generate the requested audio file. The input text is not retained after synthesis, ensuring that sensitive patient details or clinical notes remain transient and secure during the conversion process.

Input text used only for generation

Your text is sent to the engine solely to produce the audio output. It is not stored alongside your generated files, minimizing the risk of exposing medical records through long-term storage.

No training on your medical data

Unlike some consumer-grade services, we do not use your input text to train our models. Your clinical data remains yours, ensuring that proprietary or private patient information is not repurposed for algorithmic improvement.

Metadata kept for billing purposes only

We retain only request metadata—such as timestamp, character count, and status—to accurately calculate your usage and invoice your account. This data is not used for marketing or shared with third parties.

Technical specifications for developers

Sound wave illustration for: Technical specifications for developers

Clinical Audio offers a RESTful API compatible with standard OpenAI SDKs. Send a POST request to https://api.play79z.com/v1/audio/speech with a JSON body containing the model, input text, voice preset, and response format. The API returns the generated audio file directly in the response.

For documents exceeding 4096 characters, your implementation must split the text into segments and join the resulting audio files. This client-side handling ensures predictable processing for large patient guides or training manuals without relying on server-side chunking.

RESTful API with standard endpoints

The API exposes POST /v1/audio/speech for generation, GET /v1/voices for available presets, and GET /v1/models for model details. Authentication uses a Bearer token (Authorization: Bearer tts-...). Changing the SDK's base URL to https://api.play79z.com/v1 allows immediate integration using existing OpenAI client libraries.

Requests accept a model parameter ("tts-1" or "tts-1-hd") and an optional language ISO code. If omitted, the system guesses the language, defaulting to English for Latin script. The input field accepts plain text up to 4096 characters per request.

  • Endpoint: POST https://api.play79z.com/v1/audio/speech
  • Auth: Bearer token in Authorization header
  • SDK: Compatible with OpenAI Python/Node libraries

Multiple output formats including MP3 and WAV

Specify the desired audio format via the response_format field. Supported options are mp3, wav, opus, flac, and pcm. This flexibility allows integration with various electronic health record (EHR) systems or web players that prefer specific codecs. MP3 is recommended for balanced file size and quality.

Each generated file includes an inaudible watermark identifying it as synthetic speech. This helps distinguish AI-generated patient instructions from human-recorded media in clinical archives.

  • Formats: mp3, wav, opus, flac, pcm
  • No SSML or phoneme support
  • Inaudible synthetic watermark included

Rate limits suitable for batch processing

The API enforces a limit of 60 requests per minute per key (10 per minute before the first top-up). Since requests are processed sequentially, queueing may occur under load. For high-volume batch generation of training modules, implement client-side queuing to stay within limits.

Longer texts require splitting into 4096-character chunks. Your code should manage these segments, send them sequentially, and concatenate the resulting audio files. This approach ensures reliable delivery even for extensive medical documents.

  • Limit: 60 requests/minute per key
  • Processing: Sequential (queue possible)
  • Split: Client-side (max 4096 chars)

Common use cases in healthcare

Sound wave illustration for: Common use cases in healthcare

Clinical Audio enables healthcare teams to convert static medical documents into accessible audio formats, ensuring consistent communication across diverse patient populations and staff groups. By leveraging bulk generation capabilities, teams can rapidly produce audio files for large document sets without compromising on clarity or data privacy.

Audio versions of consent forms

Generate clear audio of complex consent forms using the 'atlas' voice, ensuring patients can review legal and medical details at their own pace. The API handles up to 4096 characters per request, allowing for concise yet comprehensive explanations of procedures.

  • Consistent voice across all form versions
  • Support for 23 languages including English, Spanish, and French
  • MP3 or WAV output for easy playback

Multilingual discharge instructions

Provide discharge instructions in the patient's preferred language, reducing misunderstandings and improving post-care compliance. With automatic language detection or explicit language settings, teams can quickly adapt content for diverse populations, from Arabic to Japanese.

  • 23 supported languages for global reach
  • Adjustable speed (0.25–4.0) for different patient needs
  • No data training on input text

Training modules for medical staff

Create training materials using voices like 'nova' for upbeat compliance updates or 'milo' for conversational case studies. These audio modules can be integrated into existing learning management systems, offering a scalable solution for ongoing staff education.

  • 8 distinct voice presets for varied tones
  • Fast generation: ~25 characters per second
  • Bulk processing for large document sets
Common use cases in healthcare

Get started with Clinical Audio

Sound wave illustration for: Get started with Clinical Audio

Begin by creating an account at /get-api-key/ using Google or email. You will receive a unique API key and immediate access to your dashboard, where usage metrics and balance are tracked.

Start immediately with $0.50 in free trial credit, valid for seven days. This allows you to generate approximately 50,000 characters of medical audio to validate voice quality and integration before committing to a top-up.

Connect using the standard OpenAI SDK or direct HTTP requests. Configure your base URL to https://api.play79z.com/v1, send your text via the /v1/audio/speech endpoint, and receive audio files ready for patient distribution or staff training.

Sign up and receive your API key

Visit the /get-api-key/ page to register your team account. Choose Google authentication for quick access or use email and password for traditional credential management.

Test with free trial credit

New accounts receive $0.50 in credit, covering roughly 50,000 characters. This trial lasts seven days, giving you sufficient time to test voice presets like Atlas for news-style updates or Luna for storytelling guides.

Integrate with your existing systems

Use the standard OpenAI SDK by updating the base_url to https://api.play79z.com/v1. Send JSON payloads with your API key to the /v1/audio/speech endpoint, specifying the model, voice, and desired format like MP3 or WAV.

  • Support for 23 languages with automatic detection or explicit ISO code setting.
  • Rate limit of 60 requests per minute, suitable for batch processing.
  • Input text is used only for generation and not for training.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Our patient guides simplify complex medical information for large teams to deliver clear and compassionate care.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. LibriTTS-R paper (arXiv 2305.18802)
  3. Node.js documentation
  4. TRON developer hub: TRC-20
  5. openai-python on GitHub
  6. LibriVox public-domain audiobooks
  7. Python documentation
  8. curl documentation
  9. MDN: Web Speech API
  10. Tether (USDT)
  11. IETF RFC 7845: Ogg Opus
  12. W3C WAI: making audio and video accessible

More on this site